Skip to main navigation Skip to search Skip to main content

Achievable Error Exponents for Almost Fixed-Length Binary Classification

  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We revisit the binary classification problem where the generating distribution under each hypothesis is unknown and propose a two-phase test, where each phase is a fixed-length test and the second-phase proceeds only if a reject option is decided in the first phase. We derive the achievable error exponents of both type-I and type-II error probabilities. Furthermore, we illustrate our results via numerical examples and show that the performance close to sequential test can be achieved with the much simpler and less complex almost fixed-length test. Our results generalize the design and analysis of the almost fixed-length test for binary hypothesis testing (Lalitha and Javidi, ISIT 2016) to the more practical setting of binary classification.

Original languageEnglish
Title of host publication2022 IEEE International Symposium on Information Theory, ISIT 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1336-1341
Number of pages6
ISBN (Electronic)9781665421591
DOIs
StatePublished - 2022
Event2022 IEEE International Symposium on Information Theory, ISIT 2022 - Espoo, Finland
Duration: 26 Jun 20221 Jul 2022

Publication series

NameIEEE International Symposium on Information Theory - Proceedings
Volume2022-June
ISSN (Print)2157-8095

Conference

Conference2022 IEEE International Symposium on Information Theory, ISIT 2022
Country/TerritoryFinland
CityEspoo
Period26/06/221/07/22

Keywords

  • Bayesian
  • Classification
  • Error Exponent
  • Neyman-Pearson
  • Two-phase test

Fingerprint

Dive into the research topics of 'Achievable Error Exponents for Almost Fixed-Length Binary Classification'. Together they form a unique fingerprint.

Cite this